The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Neural networks (NNs) have proven to be a very powerful tool both for one-dimensional (1D) and two-dimensional (2D) direction of arrival (DOA) estimation. By avoiding complex and time-consuming mathematical calculations, NNs estimate DOAs almost instantaneously. This feature makes them very convenient for real-time applications. Further, unlike the well known MUSIC algorithm, neural network-based...
The TSP deals with finding a shortest path through a number of cities. This seemingly simple problem is hard to solve because of the amount of possible solutions. Which is why methods that give a good suboptimal solution in a reasonable time are generally used. In this paper three methods were compared with respect to quality of solution and ease of finding correct parameters: the Integer Linear Programming...
Influence of small time-delays in coupling between noisy excitable systems on the coherence resonance and self-induced stochastic resonance is studied. Parameters of delayed coupled deterministic excitable units are chosen such that the system has only one attractor, namely the stationary state, for any value of the coupling and the time-lag. Addition of white noise induces qualitatively different...
In this paper we propose usage of neural networks in the field of meteorology especially to detect ice formation on roads. Used algorithm for building and training network is based on the road and air conditions which define ice formation on road's surface. The ability of self and supervised learning are both used to solve this problem. We used VHDL to build proposed neural network as a part of the...
Researchers in the field of Neuromorphic Engineering are looking at ways to reduce the chip space required to mimic the huge processing capacity of the human brain and to simplify algorithms to train it. Since the recent fabrication of a memristor by the Hewlett Packard Company, there is a possibility to achieve both of these. With their crucial hysteresis properties, memristors can store charge during...
The paper proposed an approach for the optimization of the water flow algorithm for the text-line segmentation. Original method assumed the hypothetical water that flows to the document image frame from left to right and vice versa. It used the water flow angle as the only parameter. Algorithm's extended version introduced a water flow function, which is given as the power function. It exploited two...
Complex-Valued Neural Networks are extensions of the classical Neural Networks. They have complex-valued weights, accept complex inputs and have more computational power than the classical ones. We discuss in this paper the training for Phase-Based Neurons, neural processing elements similar to Universal Binary Neurons, that uses as weights and bias complex numbers with unit magnitude, the phase being...
Authorship attribution, namely determination of the author of a text, may become an extraordinarily complex and sensitive job due to its relatively difficult feature extraction phase and highly nonlinear nature. This paper proposes a classification tool using committee machines consisting of multilayered perceptron neural networks (MLP) to identify the author of a text. Each expert is an individual...
In this paper we propose the new multifractal measure inspired by sigmoid activation function usually used in neural networks. By using new measure the Hölder exponent and multifractal spectrum are determined in classical way. New measure is applied to image processing, especially in texture classification. It was shown that by changing the slope of the sigmoid function different details can be extracted...
The paper tries to propose objectively existing hierarchy of control levels in Central Nervous System(CNS), based on already accomplished medical research results on Homo sapiens, i. e. Homo sapiens - sapiens CNS as well as the theory of control and the science of neural networks. Human CNS has been vague until 60 years ago. Although, there were intensive researches in the last 30 years worldwide,...
Emotional speech recognition (ESR) from the aspect of human-machine interaction (HCI) is a prerequisite for the framework of interacting partners within the HCI. This paper addresses the application of neural network (NN) in ESR. The performance of NN is tested using three different feature sets which are basis for ESR: prosodic features, spectral features and a set of their combination. The results...
One step ahead prediction of peak electricity loads based on artificial neural networks (ANN) is presented. Two architectures of ANNs were implemented to produce predictions that were used to generate the final value as an average. The time instants when daily peak loads occur are produced simultaneously. Examples will be given confirming both the feasibility of the method and the need for further...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.